Author: Ye Hong

Posted on

Congratulations to Dominik on his Master’s graduation

We congratulate Dominik on completing his Master’s degree in Geomatics Engineering at ETH Zurich. Dominik wrote his Master’s thesis at the MIE Lab, where his work earned excellent grades and strong recognition.

Dominik received the ETH Medal for an outstanding Master’s thesis and the Willi Studer Prize for the highest average grade in the program (5.83/6).

His thesis, “UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations,” introduces a self-supervised learning framework that builds unified spatial representations from multiple data sources. The model combines coordinates, street-view images, remote sensing, maps, and points of interest, and was trained and evaluated across 56 cities worldwide. The resulting embeddings support a wide range of urban analytics tasks, including housing price, energy consumption, land use, and public health predictions.

We are grateful to everyone involved in the project and proud to have supported Dominik during his time at MIE. We wish him all the best as he moves into the energy sector.

More information about Dominik’s background is available on his LinkedIn profile

Posted on

Welcome Victoria Dahmen to MIE Lab!

Victoria is a visiting PhD student at the MIE Lab in fall 2025 and spring 2026. She has been pursuing her PhD at the Chair of Traffic Engineering and Control at the Technical University of Munich since 2022, and has a background in Computational Science and Engineering and Civil Engineering. Her research interests revolve around leveraging geospatial data to address transportation challenges. This includes the use of trajectory data for bicycle routing and mode choice modelling, where she employs optimisation and machine learning techniques to develop data-driven solutions.

Methodological focus: Spatio-temporal data mining and analysis, machine learning, and predictive models.

Posted on

Martin Raubal presented at ZVR Traffic Law Conference 2025

Martin Raubal gave the keynote speech at the ZVR Traffic Law Conference 2025 at the Vienna University of Economics and Business in Austria. His talk ‘Sustainable Mobility – quo vadis’ focused on the importance of geodata and -technologies for sustainable mobility and introduced current research on electric mobility, V2G technologies, and behavior change. The slides of the talk (in German) are available here.

Posted on

New study published in Transportation Research Interdisciplinary Perspectives

Our paper on “A causal intervention framework for synthesizing mobility data and evaluating predictive neural networks” has been published open-source in Transportation Research Interdisciplinary Perspectives!

We introduced a Causal Intervention Framework that enables controlled manipulation of mobility-related behavior in synthetic location sequences. This enables us to evaluate how specific behaviors influence the performance of next-location prediction models.

We hope this offers a foundation for future research at the intersection of mobility modeling, interpretation, and explainable AI.

Check out the paper online and the corresponding code on Github!

Posted on

New JTRG paper online – Travel mode detection

Our new paper entitled “Evaluating geospatial context information for travel mode detection” was accepted at Journal of Transport Geography and is now available (open-access!) online.

How much does geospatial context information contribute to travel mode detection?

Our latest study reveals that geospatial network features, such as distance to the road network, are more critical than motion features, such as speed and acceleration, when classifying an extensive list of travel modes. Still, most land-use and land-cover features barely contribute to the task. The results are based on our extensive context representation reviews and the proposed analytical pipeline to assess the contribution of geospatial context information based on a random forest model and the SHapley Additive exPlanation (SHAP) method.

The study provides valuable guidance for feature selection, effective feature design, and building efficient travel mode detection models.

Check out the paper online and the corresponding code on Github!

Posted on

New TR_C paper online – Context-aware next location prediction

Our new paper entitled “Context-aware multi-head self-attentional neural network model for next location prediction” was accepted at Transportation Research Part C: Emerging Technologies and is now available (open-access!) online.

We present a multi-head self-attentional (MHSA) neural network that integrates location features, temporal features, and functional land use contexts for next location prediction. This comprehensive approach effectively captures movement-related spatio-temporal information, leading to state-of-the-art performance on GNSS mobility datasets.

Our analysis demonstrates that training the model on population data yields superior results by learning from collective movement patterns, surpassing the capabilities of individual-level models. Moreover, we emphasize the significance of recent past movements and weekly periodicity, showing that learning from a subset of historical mobility is sufficient to obtain an accurate location prediction result.

The proposed model represents a pivotal advancement in accurate and interpretable individual mobility prediction, and can be readily applied in downstream applications, including planning on-demand transport services, implementing mobility incentives, and suggesting alternative mobility options.

Check out the paper online and the corresponding code on Github!